# Quantifying Translation-Invariance in Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1801.01450 · HTML: https://mlsanity.com/paper/1801.01450/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2017.

## Built on by (most cited first, 30 of 30)

- [An Image is Worth 16x16 Words, What is a Video Worth?](https://mlsanity.com/paper/2103.13915/) (2021)
- [D-Former: A U-shaped Dilated Transformer for 3D Medical Image Segmentation](https://mlsanity.com/paper/2201.00462/) (2022)
- [Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives](https://mlsanity.com/paper/2206.01136/) (2022)
- [Grounding inductive biases in natural images:invariance stems from variations in data](https://mlsanity.com/paper/2106.05121/) (2021)
- [Convolutional Neural Networks Are Not Invariant to Translation, but They Can Learn to Be](https://mlsanity.com/paper/2110.05861/) (2021)
- [What Affects Learned Equivariance in Deep Image Recognition Models?](https://mlsanity.com/paper/2304.02628/) (2023)
- [Mixed Evidence for Gestalt Grouping in Deep Neural Networks](https://mlsanity.com/paper/2203.07302/) (2022)
- [Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Function](https://mlsanity.com/paper/2110.00899/) (2021)
- [Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training](https://mlsanity.com/paper/2110.01476/) (2021)
- [Representative Social Choice: From Learning Theory to AI Alignment](https://mlsanity.com/paper/2410.23953/) (2024)
- [Stride and Translation Invariance in CNNs](https://mlsanity.com/paper/2103.10097/) (2021)
- [Swinv2-Imagen: Hierarchical Vision Transformer Diffusion Models for Text-to-Image Generation](https://mlsanity.com/paper/2210.09549/) (2022)
- [Comparison of Methods Generalizing Max- and Average-Pooling](https://mlsanity.com/paper/2103.01746/) (2021)
- [Neural Photometry-guided Visual Attribute Transfer](https://mlsanity.com/paper/2112.02520/) (2021)
- [Permutation-Invariant Tabular Data Synthesis](https://mlsanity.com/paper/2211.09286/) (2022)
- [Impoola: The Power of Average Pooling for Image-Based Deep Reinforcement Learning](https://mlsanity.com/paper/2503.05546/) (2025)
- [Tracking translation invariance in CNNs](https://mlsanity.com/paper/2104.05997/) (2021)
- [CNN-based Methods for Object Recognition with High-Resolution Tactile Sensors](https://mlsanity.com/paper/2305.12417/) (2023)
- [Boosting the Local Invariance for Better Adversarial Transferability](https://mlsanity.com/paper/2503.06140/) (2025)
- [Invariance Measures for Neural Networks](https://mlsanity.com/paper/2310.17404/) (2023)
- [Quantum-secure multiparty deep learning](https://mlsanity.com/paper/2408.05629/) (2024)
- [A Novel Convolutional-Free Method for 3D Medical Imaging Segmentation](https://mlsanity.com/paper/2502.05396/) (2025)
- [Hybrid machine-learned homogenization: Bayesian data mining and convolutional neural networks](https://mlsanity.com/paper/2302.12545/) (2023)
- [Subspace-Configurable Networks](https://mlsanity.com/paper/2305.13536/) (2023)
- [Semantic Segmentation of Porosity in 4D Spatio-Temporal X-ray μ CT of Titanium Coated Ni wires using Deep Learning](https://mlsanity.com/paper/2306.14039/) (2023)
- [Graph Classification with GNNs: Optimisation, Representation and Inductive Bias](https://mlsanity.com/paper/2408.09266/) (2024)
- [3D Medical Imaging Segmentation on Non-Contrast CT](https://mlsanity.com/paper/2503.08361/) (2025)
- [A Technique for Isolating Lexically-Independent Phonetic Dependencies in Generative CNNs](https://mlsanity.com/paper/2506.09218/) (2025)
- [GASPnet: Global Agreement to Synchronize Phases](https://mlsanity.com/paper/2507.16674/) (2025)
- [Parameter-Efficient Architectural Modifications for Translation-Invariant CNNs](https://mlsanity.com/paper/2604.27870/) (2026)

## Abstract (arXiv)

A fundamental problem in object recognition is the development of image representations that are invariant to common transformations such as translation, rotation, and small deformations. There are multiple hypotheses regarding the source of translation invariance in CNNs. One idea is that translation invariance is due to the increasing receptive field size of neurons in successive convolution layers. Another possibility is that invariance is due to the pooling operation. We develop a simple a tool, the translation-sensitivity map, which we use to visualize and quantify the translation-invariance of various architectures. We obtain the surprising result that architectural choices such as the number of pooling layers and the convolution filter size have only a secondary effect on the translation-invariance of a network. Our analysis identifies training data augmentation as the most important factor in obtaining translation-invariant representations of images using convolutional neural networks.